Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Asking "what" questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    กรรมการ
    -0.07
    Trong
    -0.06
    enemy
    -0.06
    城市
    -0.06
     най
    -0.06
    ileri
    -0.06
     |=
    -0.06
    にも
    -0.06
    }>
    -0.06
    係
    -0.06
    POSITIVE LOGITS
    лся
    0.07
    _notifier
    0.07
    (work
    0.07
     ->
    0.06
    Robot
    0.06
    "io
    0.06
    perm
    0.06
    nick
    0.06
    .life
    0.06
     disjoint
    0.06
    Act Density 0.089%

    No Known Activations